Backport of #47625 to stable/1.103.x.
Cherry-picked from 6564a490f4 (main).
Adapted to the line: the batch accounting retry (track_batch_accounting in proxy_track_cost_callback and its use in check_batch_cost) is ported, while this PR's router-budget charge-once changes in router_utils/batch_utils, budget_limiter and model_max_budget_limiter are left out, since they refactor charge-once code from main (8a33b37c39, 9acf09f60d) that is not on this line. The write-started mark keys on a budget reservation only, as the search free tier is not on this line. Tests use the line's _ProxyDBLogger, and the router-budget and search-allowance assertions are dropped.
Backport of #47190 to stable/1.103.x.
Cherry-picked from 0ede0e10e7 (main).
Ported from the stable/1.104.x hand-port (3b7b5ab319). Carries the small typed table helpers that port relies on (_ManagedObjectRow protocol and the _managed_object_table/_user_table/_token_table/_team_table accessors, from the stable/1.104.x base). The poll-starvation integration test is dropped since its base and harness (#42622, integration/_support/prisma_clients) are not on this line. The 404-recovery unit test resets the litellm callback lists so a callback left by an earlier test cannot shadow it.
Backport of #47184 to stable/1.103.x.
Cherry-picked from 3fb95c8fe3 (main).
Ported from the stable/1.104.x hand-port (f7b0b09e75) onto this line's poller, which keeps LiteLLM_ManagedObjectTable and direct prisma table access. Brings the managed-files postgres_storable_json sanitizer from #45703 that this fix needs. Test files keep the line's content plus this PR's own cases.
Backport of #43935 to stable/1.103.x.
Cherry-picked from d7620c77a1 (main).
Ported from the stable/1.104.x adaptation (54f9259b40): the bridge check lives in litellm/main.py and the effort helpers keep the line's private names. Cost-map edits replay only this PR's reasoning-effort flags (gpt-6-astra and gpt-5.3-codex rows), plus supports_none_reasoning_effort=false on the azure gpt-6.1-sol rows from #46377, which the fix's tests key on. Tests built on gpt-6-sol rows (#42515), the Foundry tools-to-Responses bridge, or a full azure/eu/gpt-6-astra row are dropped since none of those are on this line.
Backport of #43738 to stable/1.103.x.
Cherry-picked from a3552c451b (main).
Prerequisite for #43935: adds the gpt-6.1-sol entry that fix corrects. Cost-map conflict resolved by appending the new entry.
The cost-map schema and its schema test also allow the *_above_272k_tokens_batches keys this row carries, which main already allows.
Backport of #47182 to stable/1.103.x.
Cherry-picked from 1212260ab1 (main).
Test-file conflict resolved by keeping the line's file and appending this PR's tests.
Calls the line's _select_model_name_for_cost_calc, which is the private name on this line.
Backport of #43955 to stable/1.103.x.
Cherry-picked from eb5295b20c (main).
Adapted to the line: the transformation lives under anthropic/experimental_pass_through, the integration tests live under tests/integration/providers, and the CLI-beta wire assertion change is dropped since that test is not on the line.
The github_copilot safeguards test uses the line's authenticator mock, since per-user Copilot sessions are not on this line.
Backport of #45686 to stable/1.103.x.
Cherry-picked from 1aee1a21ed (main).
Adapted to the line: unit test ported into tests/test_litellm; the databricks wire-test additions and the bridge-flag test edit are dropped since neither base test is on this line.
Backport of #45659 to stable/1.103.x.
Cherry-picked from fa7ad80a62 (main).
Adapted to the line: unit tests ported into tests/test_litellm; the databricks chat wire-test additions are dropped since that file is not on this line.
Backport of #45151 to stable/1.103.x.
Cherry-picked from 46d440ae96 (main).
Adapted to the line: the model-catalog Rust crate is not on this line so its two files are dropped; tests live under tests/test_litellm; conflicts resolved by keeping the line's fields plus the over-100k fields this PR adds.
Prerequisite from #39861 ported minimally: the standard above-threshold loop skips *_batches keys, so a non-batch request over 100k is not billed at the batch tier. The batch long-context tier tests are dropped since this line's batch cost path has no long-context tiers, and the runtime profile test calls the line's private _is_adaptive_thinking_model.
Backport of #45108 to stable/1.103.x.
Cherry-picked from 5cd1126870 (main).
Prerequisite for #45151: adds the claude-haiku-5-5 entries that fix corrects. Cost-map conflicts resolved by appending the new entries; schema test lives under tests/test_litellm on this line.
The cost-map schema and its schema test also allow cache_creation_input_token_cost_batches, cache_read_input_token_cost_batches and supports_anthropic_compaction, which these entries carry and main already allows.
Backport of #44460 to stable/1.103.x.
Cherry-picked from f81a3f5243 (main).
Conflict: took main's terminal_event declaration over the line's completed_event comment form.
* fix(logging): claim the async success dedup flag before the first await
Nested @client wrappers on the chat -> Responses bridge schedule two async
success tasks on one logging object. The dedup flag was checked at the top
of _async_success_handler_body but only set after several awaits; the
worker-thread base64 offload for messages >= 256 KiB yields there, so the
second task passed the same check and the request was logged twice
(two SpendLogs rows, key/team/daily spend counted twice).
Fixes#44500
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
* fix(logging): serialise async success handlers per logging object instead of claiming early
Claiming the dedup flag before the first await (previous commit) let a first
handler that is cancelled before its callbacks run (e.g. by the logging
worker's per-coroutine timeout) suppress the second one, losing the request's
success accounting. Serialise non-streaming handlers on the same Logging
object with an asyncio.Lock kept in a module-level WeakKeyDictionary: the
second handler waits, then skips if the first logged, or logs itself if the
first raised or was cancelled first. Streaming chunk logging is not locked.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
* test(integration): pin one spend row and one key charge for large bridged chat completions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): wait for the large request's spend row before asserting
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): use fixed timestamps in async success dedup tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(logging): trim the async success dedup lock comment
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logging): reset background interaction dedupe under the success dedup lock
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): use a fixed start time in the interactions logging helper
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix: claim the async success log at schedule time instead of locking the handler
Nested @client wrappers (chat over the Responses bridge, Anthropic Messages over the chat adapter) exit with one shared Logging object and each queued their own async success handler. The handler checked has_logged_async_success before its awaited work and set it after, so both could pass the check and the request was logged and billed twice.
_schedule_async_success_logging now claims the log on the Logging object synchronously through claim_async_success_log, and a later wrapper returns without enqueuing. There is no await between the check and the decision, so no lock is needed. The per-object asyncio.Lock, the WeakKeyDictionary that held it and the locked block in async_log_background_interaction_completion are gone.
Tests: the regression test moves to tests/unit/test_utils.py and drives two _dispatch_success_logging exits with one Logging object through the logging worker, asserting one log with the inner result. It fails without the claim. The cancelled-handler test is dropped since a second wrapper no longer retries. The background interaction completion test stays.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(logging): pin the background completion event order and name the innermost wrapper in the claim docstrings
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): send one bridged request and assert the inner Responses result is the logged one
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 157d96dcd0)
The two redaction tests raised the deprecated InvalidStatusCode, which the
websockets 15 asyncio client never raises, and asserted the raw 403 close
code that the handshake refusal path replaced with 1008. The refusal path
builds its close reason from the status code alone, so there is no secret
to redact there, and the handshake refusal tests already cover the error
event and the 1008 close.
Those refusal tests only passed when run after a sibling test had imported
websockets.asyncio.client, since websockets lazy-loads its exceptions
submodule. Importing InvalidStatus, Response, and Headers from their own
submodules makes them pass in any order.
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
(cherry picked from commit 38f0eb876b)
* fix(realtime): surface an upstream handshake refusal as an error event and policy close
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(realtime): tidy the handshake refusal e2e
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(realtime): keep upstream exception text out of the Azure client error
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* refactor(realtime): map handshake refusal close codes with a lookup
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 2bab39e374)
The line's integration conftest refuses any owned test missing from
contracts.json, so the backported #46099 and #46109 tests get covers marks
and manifest entries here; main has no manifest.
Backport of #46109 to stable/1.103.x.
Cherry-picked from b6df3d7fe5 (main).
Adapted to the line: unit tests live under tests/test_litellm/, and the
black-only reformat of the existing completion-responses tests is not carried.
Backport of #46099 to stable/1.103.x.
Cherry-picked from 4b7b8efd4c (main).
Adapted to the line: unit test lives under tests/test_litellm/, and only this
PR's own tests are carried into the integration file.
Prerequisite for the backport of #46099 to stable/1.103.x: its integration
tests import list_value, which reached main in #43981.
Hand-ported from 43f07d0bd8 (main).
Partial backport to stable/1.103.x: only the text completion endpoint test moves off the retired gpt-3.5-turbo-instruct to openai/gpt-5.4-nano with reasoning off. This line predates the OpenAI SDK rewrite of the test, so reasoning_effort goes through EndpointsClient.text_completions instead of extra_body. The SAIL, spend-log and coverage registry repairs are not needed for this line's e2e suite
(cherry picked from commit e61733b170)
Partial backport to stable/1.103.x: only the Together AI structured-output e2e case moves to the hybrid reasoning backend with reasoning off, since the reasoning-only model it picked returned no content. The CI infrastructure and other test repairs are not needed for this line's e2e suite
(cherry picked from commit 6ca90b927c)
* revert(responses): revert "fix(responses): keep gpt-5.4/5.5 tool calls on chat and merge bridged tool calls into one choice" (#44295)
This reverts commit ca1994e403.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(responses): merge bridged tool calls into the same choice as the text
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 5724117116)
* fix(proxy): stamp the client alias on a copy of each streamed chunk so pricing sees the deployment model
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): streamed alias matching a capability rule bills the deployment price
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(spend): assert every streamed chunk carries the client alias
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(logging): log the client alias on the priced streamed response, the same as non-streamed
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 7b432d78d2)
schema.prisma still declares the LiteLLM_SpendLogs (api_key, startTime) and (litellm_call_id) indexes while their migrations are now SELECT 1, so the v1 resolver's drift script recreated both with a blocking CREATE INDEX at boot. The drift script now drops those two statements before it is applied, matching filter_request_log_index_diff on main. The key metadata recovery fixture builds its index directly and the schema sync test exempts the two indexes.
ENFORCE_PRISMA_MIGRATION_CHECK now defaults to true in both the proxy CLI and the standalone migration entrypoint, with ENFORCE_PRISMA_MIGRATION_CHECK=false or --no-enforce_prisma_migration_check as the opt-out. The two LiteLLM_SpendLogs index migrations become SELECT 1 so operators build those indexes online by hand.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(proxy): restore pre-config-wins handling of pass-through endpoints
Config-wins (#41779) made general_settings.pass_through_endpoints a config-owned key. The DB reader then got the config list back as if it were DB rows, re-registered each entry without forward_headers on every DB sync, and the stripped copy won the route lookup, so a config pass-through with forward_headers: true stopped forwarding Authorization. UI create, update and delete of pass-throughs were also rejected while the config declared any.
This puts pass-throughs back on their pre-#41779 path: the settings store no longer lets the config own the key, the config list is captured env-resolved at load_config, each DB sync merges DB entries with config entries on paths the DB does not declare, and /config/field/info reads the stored rows only. A UI pass-through write re-applies that merge immediately so the config entries stay served until the next sync.
* fix(proxy): keep config pass-throughs in every reload of the merged list
get_config now returns DB pass-throughs plus config ones on other paths,
each DB sync republishes that merged list, and /config/field/info reads
pass_through_endpoints from the DB row so a UI write never drops stored
entries when models are not stored in the DB
* fix(proxy): keep serving pass-throughs while the config file reloads
load_yaml cleared the runtime pass-through list, so auth: false routes
answered 401 while get_config awaited the database
* fix(proxy): read stored pass-throughs from the writer before a UI write
A lagging read replica could return an older list, and the UI create and
edit flows write the whole field back
* fix(proxy): apply config file pass-through auth changes on reload
The kept runtime list was merged as if it were DB entries, so an edited
config entry on the same path was dropped. Merge the stored DB row with
the fresh config instead, and give the field-info test mock a writer
* fix(proxy): keep pass-throughs served while a DB sync reads the database
get_config resets the stored DB rows before reading them again, which
cleared the served pass-through list and made auth: false routes answer
401 for the length of the read
* refactor(proxy): move the settings store reload out of the loop
basedpyright rejects a Final variable assigned inside a loop
(cherry picked from commit 2eb2bf130b)
Hand-ported prerequisite for the #43642 backport to stable/1.103.x.
Taken from dd636373229b1ab3bfb2ed5b9b17b0ebd68b3ac7 (#43288, main), scratch_database only.
The proxy never forwards client anthropic-beta headers to azure_ai, so Foundry
400s on safeguards without the beta. Add it on the provider side when the request
carries safeguards, the way the Vertex path does.
Foundry answers safeguards without the dangerous-tool-use-2026-09-03 beta
with a 400, and the azure_ai beta map dropped that beta, so Claude Code auto
mode requests through the gateway turned from 200 into 400 once safeguards
started passing through
Adds a test-quality-ok marker on the one patch.object the picked Vertex test needs, since the GCP token exchange runs before the faked HTTP boundary. Test-only, no runtime change.
Backport of #42288 to stable/1.103.x.
Cherry-picked from fc82f6e8fa (main, first parent). Its Bedrock Mantle beta map and Mantle-only test are left out, since this line has no bedrock_mantle beta map and its Mantle messages path reuses the Bedrock Invoke one.
* fix(proxy): unregister logging callbacks removed from the stored config
POST /config/callback/delete saved the config and resynced, but the resync only
ever added callbacks, so a deleted callback kept exporting and kept showing in
/get/config/callbacks as read-only on every worker.
ProxyConfig now tracks which callback list entries each DB config sync
registered and unregisters them once the stored config stops listing them.
Callbacks it did not register (YAML, code) are never touched, and a failed
config load skips the sync instead of treating the config as empty.
* refactor(proxy): keep callback sync comprehensions to one for clause
* test(e2e): tolerate provider-side flakes on five full-suite cells (#42628)
* test(e2e): tolerate provider-side flakes on five full-suite cells
Mistral OCR retries a provider-relayed 429 with backoff, the Vertex vision
probe turns reasoning off so its 32 tokens go to the answer, the Vertex
cache cell spaces eight never-seen prefixes 15s apart around Google's
nondeterministic minimum-token rejection and prices the cached tokens
instead of prompt_tokens, and the Azure content-policy cell resends the
jailbreak prompt while Azure skips its filter
* test(e2e): shorten the new helper docstrings
* test(e2e): accept a relayed provider 429 on the rust OCR cells
The gateway already retries a provider 429 three times per call and the
Mistral key is shared across pipelines, so a throttle can hold across all
four attempts of the OCR cell. After the bounded retries the cell now
accepts the gateway's faithful relay of the provider's 429 (throttling_error,
code 429) as its second expected outcome; the gateway's own 429 and any
other error still fail the cell at once.
* test(e2e): drop the harness unit tests, the live cells cover the helpers
---------
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
(cherry picked from commit 41ca4656cd)
* fix(streaming): keep litellm Usage on text-completion usage chunks (#43047)
* fix(streaming): keep litellm Usage on text-completion usage chunks
* fix(streaming): convert provider usage to litellm Usage instead of dropping it
(cherry picked from commit be35b22dfc)
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
The batch cleanup leftover warning used a class defined in a test-directory module. The xdist controller cannot import it, so an uncaught leftover warning crashed the whole e2e run. It is now a plain UserWarning.
The integration harness backport missed the workers option and Gateway.request headers that the OTel conversation id tests use.
Backports the batch cleanup half of #43321 so an Azure cancel still in progress after 120s leaves a warning instead of a teardown error, and points the MCP Tools UI test at DeepWiki's renamed ask_wiki_question tool.
Adds the OwnedProxy harness the #42486 backport's OTel test imports, registers the #43029 backport's spend flush test in contracts.json with its covers marker, and aligns the MCP tool failure assertion with main.
* fix(caching): stand default cache points down when extra_body hides a direct client mark
On native /v1/messages the extra_body envelope is dropped, so a client tool mark or root cache_control reaches Anthropic even when extra_body overrides it. The stand-down check only counted the envelope-merged view and injected two default marks on top of the client's.
(cherry picked from commit 01ef7c4725)
* fix(caching): keep chat completions on the envelope-merged mark count for the default stand-down
Chat completions merge extra_body over the request, so a direct tool mark that extra_body replaces never reaches the provider there. Only /v1/messages, where the native transforms drop the envelope, needs to count marks on both sides.
(cherry picked from commit a9c5fa760e)
* feat(otel): emit gen_ai.conversation.id from the caller's session id on v2 LLM spans (#42486)
* feat(otel): emit gen_ai.conversation.id from the caller's session id on v2 LLM spans
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): keep the caller's header session under missing_session_id: generate and read replayed payload session ids
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): drop only the proxy-minted session id so a caller id on the other metadata key survives
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): keep a replayed session id hidden when it only echoes the payload trace id
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): keep a replayed session id even when the payload trace id fell back to it
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(otel): stop reading the replayed payload's session id, the generated marker does not survive replay
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): audit gen_ai.conversation.id on otel v2 spans through a real proxy, sink and postgres
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): keep otel conversation rigs alive for the whole session so shuffled shards do not reboot the proxy per test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel): stop the audit rig proxies from probing sibling test peers for model info
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel): record accepted OTLP batches in the sink instead of mutating the collector
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(otel): guard the accepted batch deque so snapshots cannot race sink appends
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: mrinal <mrinal@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: yucheng <yucheng@berri.ai>
(cherry picked from commit a3196907e4)
* fix(jwt): accept a team alias in x-litellm-team-id (#42445)
* fix(jwt): accept a team alias in x-litellm-team-id
The header only matched canonical team ids, so a JWT caller selecting one of their teams by its alias got a 403 even though they belonged to it. The header value is now resolved through the existing alias lookup before the JWT allowed-team check and the DB membership fallback, while a value that is already a team id never costs an alias lookup and denials keep naming the value the caller sent
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(jwt): only alias a header team id the database provably lacks
Under fallback_to_db_teams a header value whose team row read fails for any reason other than TeamNotFoundError now keeps the membership denial instead of falling through to the alias lookup, so a degraded read cannot select a different team that carries the value as an alias. Drops the HeaderTeam docstring that only restated its fields
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 071cb49d32)
* fix(jwt): say x-litellm-team-id matched no team id or alias in the 403 (#42495)
* fix(jwt): say x-litellm-team-id matched no team id or alias in the 403
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(jwt): tell the caller when x-litellm-team-id names an alias shared by several teams
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* fix(jwt): deny a shared x-litellm-team-id alias exactly like an unknown value
A distinct 403 for an alias several teams share was raised before the
allowed-teams check, so any JWT could probe which aliases exist. The
alias lookup now treats the duplicate as a miss, and both denials say
the value does not resolve to a team id or a unique team alias, which
is true for unknown, unauthorized and duplicate values alike
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 08639fcf42)
* fix(jwt): let x-litellm-team-id select DB membership teams when the token also carries a team claim (#43206)
* fix(jwt): let x-litellm-team-id select DB membership teams when the token also carries a team claim
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* docs(jwt): describe header team selection under fallback_to_db_teams
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---------
Co-authored-by: yassin <yassin@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
(cherry picked from commit 7b4fd47c6e)
---------
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mrinal <mrinal@berri.ai>
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: ryan <ryan@berri.ai>
Co-authored-by: yassin <yassin@berri.ai>
* fix: apply configured cache_control_injection_points beside client cache_control marks (#41956)
(cherry picked from commit d8267d507d)
* fix(token_counter): count replayed redacted_thinking blocks so prompt_caching keeps pinning (#42069)
(cherry picked from commit 0e7cf5113e)
* fix(mcp): return camelCase tool keys from /v1/mcp/tools after the SDK 2 upgrade (#42352)
(cherry picked from commit 5eb4e30f29)
* fix(rust_bridge): keep the Messages route on Python until the Rust path is ready (#42517)
rc/1.103.0 has no token counter or tokenizer routes in the catalog, so only the Messages rule moves to PYTHON_ONLY
(cherry picked from commit 85ed18e8f2)
* fix(proxy): stop leaking periodic tasks on every DB config reload (#42784)
(cherry picked from commit fc87a06f00)
---------
Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Prisma types a raw array parameter from the first batch a connection sees. After a flush in
which every member cost was a whole number (a free model), the connection's cached statement
expected int8[] and every later fractional batch on it failed with "improper binary format in
array element", so member spend silently stopped landing while team spend kept rising.
The rows now travel as one JSON document unpacked by jsonb_to_recordset with the column types
declared in SQL, so Postgres types the numbers and the batch shape no longer matters.
(cherry picked from commit 5e4b1b9df0)
Co-authored-by: ryan-crabbe-berri <ryan@berri.ai>
Reverts the code from #41324 (merge 87694c26ef) and #41293 (merge 2e46b10320).
The LiteLLM_DailyGlobalSpend model and migration stay so databases that applied
rc.1 keep a consistent table and rollup marker when the feature returns.
